Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison

• URL: http://arxiv.org/abs/2407.07450v1
• Date: Wed, 10 Jul 2024 08:07:55 GMT
• Title: Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison
• Authors: Simone Göttlich, Jacob Heieck, Andreas Neuenkirch,
• Abstract summary: We explore two methods based on low-discrepancy points to reduce large data sets in order to train neural networks. The first is the method of Dick and Feischl, which relies on digital nets and an averaging procedure. We construct a second method, which again uses digital nets, but Voronoi clustering instead of averaging.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-discrepancy points (also called Quasi-Monte Carlo points) are deterministically and cleverly chosen point sets in the unit cube, which provide an approximation of the uniform distribution. We explore two methods based on such low-discrepancy points to reduce large data sets in order to train neural networks. The first one is the method of Dick and Feischl [4], which relies on digital nets and an averaging procedure. Motivated by our experimental findings, we construct a second method, which again uses digital nets, but Voronoi clustering instead of averaging. Both methods are compared to the supercompress approach of [14], which is a variant of the K-means clustering algorithm. The comparison is done in terms of the compression error for different objective functions and the accuracy of the training of a neural network.

Related papers

• What to Do When Your Discrete Optimization Is the Size of a Neural Network? [24.546550334179486]
  Machine learning applications using neural networks involve solving discrete optimization problems. classical approaches used in discrete settings do not scale well to large neural networks. We take continuation path (CP) methods to represent using purely the former and Monte Carlo (MC) methods to represent the latter.
  arXiv  Detail & Related papers  (2024-02-15T21:57:43Z)
• Learning A Disentangling Representation For PU Learning [18.94726971543125]
  We propose to learn a neural network-based data representation using a loss function that can be used to project the unlabeled data into two clusters. We conduct experiments on simulated PU data that demonstrate the improved performance of our proposed method compared to the current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-10-05T18:33:32Z)
• Low-rank extended Kalman filtering for online learning of neural networks from streaming data [71.97861600347959]
  We propose an efficient online approximate Bayesian inference algorithm for estimating the parameters of a nonlinear function from a potentially non-stationary data stream. The method is based on the extended Kalman filter (EKF), but uses a novel low-rank plus diagonal decomposition of the posterior matrix. In contrast to methods based on variational inference, our method is fully deterministic, and does not require step-size tuning.
  arXiv  Detail & Related papers  (2023-05-31T03:48:49Z)
• Rethinking k-means from manifold learning perspective [122.38667613245151]
  We present a new clustering algorithm which directly detects clusters of data without mean estimation. Specifically, we construct distance matrix between data points by Butterworth filter. To well exploit the complementary information embedded in different views, we leverage the tensor Schatten p-norm regularization.
  arXiv  Detail & Related papers  (2023-05-12T03:01:41Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks [5.942847925681103]
  We study distributed classification, which can be employed in situations were data cannot be stored at a central location nor shared. We propose a more efficient solution for distributed classification by making use of a lossy compression approach applied when sharing the local classifiers with other agents.
  arXiv  Detail & Related papers  (2021-06-02T01:33:56Z)
• Determinantal consensus clustering [77.34726150561087]
  We propose the use of determinantal point processes or DPP for the random restart of clustering algorithms. DPPs favor diversity of the center points within subsets. We show through simulations that, contrary to DPP, this technique fails both to ensure diversity, and to obtain a good coverage of all data facets.
  arXiv  Detail & Related papers  (2021-02-07T23:48:24Z)
• Deep Magnification-Flexible Upsampling over 3D Point Clouds [103.09504572409449]
  We propose a novel end-to-end learning-based framework to generate dense point clouds. We first formulate the problem explicitly, which boils down to determining the weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted weights as well as the high-order refinements.
  arXiv  Detail & Related papers  (2020-11-25T14:00:18Z)
• Data-Independent Structured Pruning of Neural Networks via Coresets [21.436706159840018]
  We propose the first efficient structured pruning algorithm with a provable trade-off between its compression rate and the approximation error for any future test sample. Unlike previous works, our coreset is data independent, meaning that it provably guarantees the accuracy of the function for any input $xin mathbbRd$, including an adversarial one.
  arXiv  Detail & Related papers  (2020-08-19T08:03:09Z)
• PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning [62.440827696638664]
  We introduce a simple algorithm that directly compresses the model differences between neighboring workers. Inspired by the PowerSGD for centralized deep learning, this algorithm uses power steps to maximize the information transferred per bit.
  arXiv  Detail & Related papers  (2020-08-04T09:14:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.